Hugging Face's logo

andge
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
andge commited on
Commit
2745fba
•
1 Parent(s): 07a630a

Initial commit

Browse files
Files changed (12) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +1 -1
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +1 -1
  5. dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version +1 -1
  6. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  8. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  10. replay.mp4 +2 -2
  11. results.json +1 -1
  12. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 527.00 +/- 140.72
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -67,7 +67,7 @@ OrderedDict([('batch_size', 32),
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
- ('n_timesteps', 1000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 630.00 +/- 214.21
20
  name: mean_reward
21
  verified: false
22
  ---
 
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 2000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2174195190
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 92889357
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 2000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46dda3b7b6a37d011a59f315c996ee1e46c121e781be9efc498e1c025275598a
3
  size 27224809
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3db7373bf32faaa07b51bef49b6155635c2e2b69ce07b49549ac22df6a902e49
3
  size 27224809
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 1.7.0a11
 
1
+ 1.7.0a12
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8a41a454b4c787a9360f36226272806f311ed305b9e3629a9905c5b42880836
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d486548b1912bfcda750e6ec5a233b91fe513fa64e764056d1310b2ce06e669
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4eee58021733cb51982f98076d8695508d9286b4564a164a8a54439f706fef8f
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ec4537e63ab8a5fc5b3d4d72e1647be7c8940c78b18f55172036ea0be12fd53
3
  size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,6 +1,6 @@
1
  - OS: Linux-5.10.133+-x86_64-with-glibc2.27 # 1 SMP Fri Aug 26 08:44:51 UTC 2022
2
  - Python: 3.8.16
3
- - Stable-Baselines3: 1.7.0a11
4
  - PyTorch: 1.13.0+cu116
5
  - GPU Enabled: True
6
  - Numpy: 1.21.6
 
1
  - OS: Linux-5.10.133+-x86_64-with-glibc2.27 # 1 SMP Fri Aug 26 08:44:51 UTC 2022
2
  - Python: 3.8.16
3
+ - Stable-Baselines3: 1.7.0a12
4
  - PyTorch: 1.13.0+cu116
5
  - GPU Enabled: True
6
  - Numpy: 1.21.6
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbe8f9f5a34845f2645615d5e9e1727e04626e2807aaaa2ca3bf868ec724f478
3
- size 183750
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0edce051c934d7263ed62dc3f5b3b296114b12ec45f69242896d10ca8fca5a47
3
+ size 234045
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 527.0, "std_reward": 140.71602609511115, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-04T13:00:44.042955"}
 
1
+ {"mean_reward": 630.0, "std_reward": 214.20784299366818, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-05T15:51:52.082719"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef8ea1ea3bf81eab964c22b07f0a805f9f37cbf635a6f980a59755418a257735
3
- size 36767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfe174c5d23a8dc25739bbca815382f864d4870fa3426a88581a79878552e5bc
3
+ size 62266